INDEX

Explanations

references to accessing and modifying data within a specific context or framework

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

htable

-0.17

ulace

-0.17

ikat

-0.15

nis

-0.15

thing

-0.14

oredProcedure

-0.14

_stuff

-0.14

æľīåħ³

-0.14

 Years

-0.14

timeofday

-0.14

POSITIVE LOGITS

 stead

0.21

ital

0.20

 case

0.19

 theory

0.17

-place

0.17

 reality

0.17

 begging

0.16

its

0.16

italize

0.16

ittle

0.16

Activations Density 0.285%

references to accessing and modifying data within a specific context or framework

No Comments

No Known Activations